Run ADR conformance checks, explain failures, and identify required ADR/doc updates for the current change.
69
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is concise and specific about what the skill does, clearly listing three concrete actions related to ADR conformance. However, it lacks an explicit 'Use when...' clause and could benefit from expanded trigger terms including the full 'architecture decision record' phrase and common user language variations.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks about ADR compliance, architecture decision conformance, or whether a code change aligns with documented architectural decisions.'
Expand the acronym ADR at least once (e.g., 'ADR (Architecture Decision Record)') and include natural trigger terms like 'architecture review', 'decision record', 'compliance check', or 'documentation updates'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Run ADR conformance checks', 'explain failures', and 'identify required ADR/doc updates for the current change'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | The 'what' is well-covered (run conformance checks, explain failures, identify updates), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The phrase 'for the current change' implies context but doesn't explicitly state when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'ADR', 'conformance checks', and 'doc updates', but misses common variations users might say such as 'architecture decision record', 'architecture review', 'compliance check', or 'documentation'. Users unfamiliar with the acronym ADR may not trigger this skill. | 2 / 3 |
Distinctiveness Conflict Risk | ADR conformance checking is a very specific niche. The combination of 'ADR', 'conformance checks', and 'doc updates for the current change' creates a distinct identity unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides clear, actionable guidance for ADR conformance checking. It includes executable commands, specific file paths, explicit validation loops, and a structured output format. The workflow is appropriately sequenced with feedback loops for error recovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what ADRs are or how git works. The skill assumes Claude knows the concepts and focuses purely on the specific workflow and project-specific details. | 3 / 3 |
Actionability | Provides exact executable commands (git diff, adr_guard.py invocations), specific file paths to check (docs/adr/exceptions.yaml, docs/adr/**), and concrete field names for waivers (rule_id, owner, reason, expires_on). Copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear sequential steps with explicit validation checkpoints: fast guard → fix and re-run loop → guardrail file verification → CI profile as final gate. The feedback loop in step 3 (fix → re-run) is explicitly stated for this potentially destructive/compliance-critical operation. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single focused task, the content is well-organized with clear sections (Steps, Output). No bundle files are provided, but none are needed—the skill references project paths directly and doesn't require supplementary documentation. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
a7c1694
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.